Contrastive Regularization For Multimodal Emotion Recognition Using Audio And Text

Abstract

Speech emotion recognition is a challenge and an important step towards more natural human-computer interaction (HCI). The popular approach is multimodal emotion recognition based on model-level fusion, which means that the multimodal signals can be encoded to acquire embeddings, and then the embeddings are concatenated together for the final classification. However, due to the influence of noise or other factors, each modality does not always tend to the same emotional category, which affects the generalization of a model. In this paper, we propose a novel regularization method via contrastive learning for multimodal emotion recognition using audio and text. By introducing a discriminator to distinguish the difference between the same and different emotional pairs, we explicitly restrict the latent code of each modality to contain the same emotional information, so as to reduce the noise interference and get more discriminative representation. Experiments are performed on the standard

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyqian2022contrastive

Related papers

• Multimodal Speech Emotion Recognition Using Audio And Text (2018)18.02
• Learning Alignment For Multimodal Emotion Recognition From Speech (2019)15.22
• Multimodal Speech Emotion Recognition And Ambiguity Resolution (2019)0.00
• Cross-modal Fusion Techniques For Utterance-level Emotion Recognition From Text And Speech (2023)9.59
• Speech Emotion Recognition Via Contrastive Loss Under Siamese Networks (2019)12.17
• Fusion Approaches For Emotion Recognition From Speech Using Acoustic And Text-based Features (2024)12.25
• Multistage Linguistic Conditioning Of Convolutional Layers For Speech Emotion Recognition (2021)9.23
• Jointly Fine-tuning "bert-like" Self Supervised Models To Improve Multimodal Speech Emotion Recognition (2020)13.74